Add new textToKnowledgeGraph reader source#1487
Merged
bgyori merged 25 commits intogyorilab:masterfrom Dec 19, 2025
Merged
Conversation
…nd metadata propagation and Add V2 mock test for live BEL extraction wrapper using monkeypatched textToKnowledgeGraph
…le PyBEL processor outputs safely
…sistent metadata attachment
…on and delete the other two test files
bgyori
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
(rewritten by @bgyori ) This PR adds a new source module wrapping the textToKnowledgeGraph or
tkgreader which uses LLMs to produce BEL statements from text. Key to the integration is that the existingindra.sources.belmodule can be leveraged to process BEL statement strings produced bytkg.The new API supports both invoking
tkgas a package to process PubMedCentral articles or process existing output files fromtkgoffline.One note is that
tkgoften produces BEL strings that are not valid. These are effectively skipped sinceindra.sources.belwill not be able to process them, and overall we still get many valid statements. It is possible that with additional rule-based string manipulation, some of these can be turned into valid BEL but fixing these upstream may be more effective.